ssic-linux-users — User discussion

Re: [SSI-users] Monitoring OpenSSI

[Mulyadi S. <mul...@gm...>]

Hi....

On Thu, Nov 4, 2010 at 23:41, Cumberland, Lonnie
<lon...@ni...> wrote:
> It actually turns out that the “demo-proclib” application does, in fact,
> load balance across the nodes, but that the EGSnrc Monte Carlo software that
> I have also been testing does not load balance across the nodes for some
> reason even though multiple instances are started.

Quite likely they are either:
- use System V shared memory
- pthreads based

or maybe...."live" not long enough...thus the benefit of migration is
very small...

Maybe there are other possibilities....so I might be totally wrong here.

NB: for monitoring load across nodes, have you tried ganglia or cacti?
maybe it's not as simple as top, but IMO it might serve you well.

-- 
regards,

Mulyadi Santosa
Freelance Linux trainer and consultant

blog: the-hydra.blogspot.com
training: mulyaditraining.blogspot.com

Re: [SSI-users] Monitoring OpenSSI

[Cumberland, L. <lon...@ni...>]

Hello all,

An update on my testing.

It actually turns out that the "demo-proclib" application does, in fact, load balance across the nodes, but that the EGSnrc Monte Carlo software that I have also been testing does not load balance across the nodes for some reason even though multiple instances are started.

Thanks and have a great day,
Lonnie Cumberland, Prof.
Physicist



From: Cumberland, Lonnie [mailto:lon...@ni...]
Sent: Thursday, November 04, 2010 12:28 PM
To: ssi...@li...
Subject: Re: [SSI-users] Monitoring OpenSSI

Greetings All,

I have just come across the "load" command that seems to give me the loading on the cluster. The strange thing is that even though I am running a demo app in "bash-ll" the load command only shows the main node load changing.

Any ideas on this?

Thanks and have a great day,
Lonnie Cumberland, Prof.
Physicist



From: Cumberland, Lonnie [mailto:lon...@ni...]
Sent: Thursday, November 04, 2010 11:37 AM
To: ssi...@li...
Subject: [SSI-users] Monitoring OpenSSI

Greetings All,

I hope that everyone is has been doing well.

We have been testing OpenSSI on our small cluster to see how it performs and thus far, it has done pretty well with only a few problems.

One thing that I have not been able to find yet is a way to monitor the cluster and node activity.  I was able to run a demo-proclib application to see who the cluster performs (Thanks Scott) but have yet to find an application that can monitor the cluster for load and stuff like that.

I think that in Mosix there is an application that shows the load and processes of each node and probably OpenSSI has the same thing as well.

Any help would be greatly appreciated.

Thanks and have a great day,
Lonnie Cumberland, Prof.
Physicist

Re: [SSI-users] Monitoring OpenSSI

[Cumberland, L. <lon...@ni...>]

Greetings All,

I have just come across the "load" command that seems to give me the loading on the cluster. The strange thing is that even though I am running a demo app in "bash-ll" the load command only shows the main node load changing.

Any ideas on this?

Thanks and have a great day,
Lonnie Cumberland, Prof.
Physicist



From: Cumberland, Lonnie [mailto:lon...@ni...]
Sent: Thursday, November 04, 2010 11:37 AM
To: ssi...@li...
Subject: [SSI-users] Monitoring OpenSSI

Greetings All,

I hope that everyone is has been doing well.

We have been testing OpenSSI on our small cluster to see how it performs and thus far, it has done pretty well with only a few problems.

One thing that I have not been able to find yet is a way to monitor the cluster and node activity.  I was able to run a demo-proclib application to see who the cluster performs (Thanks Scott) but have yet to find an application that can monitor the cluster for load and stuff like that.

I think that in Mosix there is an application that shows the load and processes of each node and probably OpenSSI has the same thing as well.

Any help would be greatly appreciated.

Thanks and have a great day,
Lonnie Cumberland, Prof.
Physicist

[SSI-users] Monitoring OpenSSI

[Cumberland, L. <lon...@ni...>]

Greetings All,

I hope that everyone is has been doing well.

We have been testing OpenSSI on our small cluster to see how it performs and thus far, it has done pretty well with only a few problems.

One thing that I have not been able to find yet is a way to monitor the cluster and node activity.  I was able to run a demo-proclib application to see who the cluster performs (Thanks Scott) but have yet to find an application that can monitor the cluster for load and stuff like that.

I think that in Mosix there is an application that shows the load and processes of each node and probably OpenSSI has the same thing as well.

Any help would be greatly appreciated.

Thanks and have a great day,
Lonnie Cumberland, Prof.
Physicist

Re: [SSI-users] more information about CFS

[John H. <jo...@Ca...>]

Alceu Rodrigues de Freitas Junior wrote:
> Hello guys,
>
> I'm looking for more information about CFS (Cluster File System) on 
> OpenSSI.
>   
CFS on OpenSSI is a descendant of the CFS system written by Locus for 
the "Transparent Network Computing" product. which was adopted by OSF as 
their network file system.  (It is currently included in HP's 
TruClusters product.)

The biggest difference between CFS and NFS is that CFS implements full 
Posix semantics - file locking, cache coherency and so on.

In terms of implementation CFS consists of two parts:

Simple file operations like remove file, rename and so on are done by 
remote procedure calls from the client machine to the CFS server.

I/O is intimately connected to distributed shared memory - reading a 
file is the process of mapping pages of the file into the memory of the 
node doing the read.  Writing a file is mapping the pages of the file 
into memory and changing them.   At any one moment a page may be 
writable by one node, or readable by many nodes.  Synchronisation 
between nodes is done by exchanging a "token".

For example: say a process on a node wants to read a page of a file.   
The node either has that page in its cache, in which case all is well, 
the data is just copied from the cache into the reading process, or the 
node asks the CFS server for a copy of the page.  The CFS server will 
get the page into it's own cache (if it's not already there) and send a 
copy to the reading node. (*)

Now what happens if a process wants to write a page?  If the page is 
already in the nodes cache, marked writable, all goes as normal.  If not 
the node asks the CFS server for write access to the page.   The CFS 
server will have to tell all people who currently have read access to 
discard their copy, and send a writable copy of the page to the client.

(* Of course I left a step out here - if the page is currently being 
written by some other node it will have to send back its copy, and mark 
it read only).

Re: [SSI-users] more information about CFS

[Greg F. <gre...@gm...>]

On Mon, Nov 1, 2010 at 12:53 PM, Alceu Rodrigues de Freitas Junior <
gla...@ya...> wrote:

> Hello guys,
>
> I'm looking for more information about CFS (Cluster File System) on
> OpenSSI.
>
> I already checked in the wiki, README.cfs and README.hardmounts but I'm
> looking for more introductory information like how does it works, if it
> uses NFS or not, etc.
>
> Could you please provide some more info about that? A link or two would
> be terrific.
>
> Thanks in advance,
> Alceu
>
>
>
I haven't worked on the CFS code myself, but I'm fairly sure it is NOT nfs
based.  ie. NFS is not used internally in the cluster to create a CFS
filesystem.

You can nfs export a CFS filesystem to computers outside the cluster, or a
openSSI cluster can mount externally provided NFS share.

Thus, NFS is a way for a openSSI cluster to work with the outside world, but
it is not used internally to the cluster itself.

CFS simply takes a local volume and makes it accessible as a filesystem in
parallel to all the nodes in the cluster.  For failover protection, you can
incorporate drbd.  drbd is not in the vanilla kernel code that openSSI is
compatible with.

(ie. It went into the vanilla kernel around 2.6.32 I think which is far
newer than the openSSI supported kernels).

Thus if you want CFS with failover on the cheap you should look at drbd.

You can also use CFS with externally provided raw volumes such as a FC SAN
or iSCSI SAN would provide.  In that case you need to have only one node at
a time accessing the raw volume.  It would in turn layer the CFS logic on
top and share the volume out to the other nodes as a filesystem.

You would need to implement node failover for the access/cfs/export
functionality to ensure the cluster could continue on in event of failure of
the node providing the connection to the raw volume.

Greg

[SSI-users] more information about CFS

[Alceu R. de F. J. <gla...@ya...>]

Hello guys,

I'm looking for more information about CFS (Cluster File System) on 
OpenSSI.

I already checked in the wiki, README.cfs and README.hardmounts but I'm 
looking for more introductory information like how does it works, if it 
uses NFS or not, etc.

Could you please provide some more info about that? A link or two would 
be terrific.

Thanks in advance,
Alceu

Re: [SSI-users] Cannot find /sbin/mount.nfs

[Mulyadi S. <mul...@gm...>]

Hi Nathan...

On Mon, Nov 1, 2010 at 12:04, Nathan Rozentals
<nat...@ho...> wrote:
> Hey mulyadi,
> Many thanks for your reply.
> I have built the nfs-utils package from source, but still no mount.nfs.

really? Hm..well, no idea then...that's what I get when running:
$ rpm -qf /sbin/mount.nfs
nfs-utils-<version  number>

> Is it present in the CentOS tree ?

You mean, is it in base repository? I believe yes......

> Can you mount an nfs share in your CentOS cluster ?

I didn't have any CentOS cluster here...so that fact is taken from my
workstation.

-- 
regards,

Mulyadi Santosa
Freelance Linux trainer and consultant

blog: the-hydra.blogspot.com
training: mulyaditraining.blogspot.com

Re: [SSI-users] Cannot find /sbin/mount.nfs

[Mulyadi S. <mul...@gm...>]

On Mon, Nov 1, 2010 at 08:03, Nathan Rozentals
<nat...@ho...> wrote:
> I am trying to use nfs mounts on my 1.9.6 cluster on Debian, and mount is
> failing due to there being no /sbin/mount.nfs.
> I have tried compiling nfs-common ( which builds and installs fine), but to
> no avail.
> How do I re-build mount.nfs ?

Just giving you idea, in CentOS 5.x mount.nfs is in nfs-utils package


-- 
regards,

Mulyadi Santosa
Freelance Linux trainer and consultant

blog: the-hydra.blogspot.com
training: mulyaditraining.blogspot.com

[SSI-users] Cannot find /sbin/mount.nfs

[Nathan R. <nat...@ho...>]

I am trying to use nfs mounts on my 1.9.6 cluster on Debian, and mount is failing due to there being no /sbin/mount.nfs.
I have tried compiling nfs-common ( which builds and installs fine), but to no avail.
How do I re-build mount.nfs ?
  		 	   		  

Re: [SSI-users] Memory Migration in Realtime Linux Kernels

[Roger T. <rog...@gm...>]

Hi,

Sounds like you are talking about the feature to reduce memory latency on
NUMA which, if I'm not wrong, operates at lower level than shared memory
segments.  We have or will have the feature when OpenSSI is ported to a base
kernel with this feature.

Also the main feature of real-time Linux is reduced schedule latencies by
pre-empting more aggressively, not memory migration...

-Roger

On Thu, Oct 21, 2010 at 10:39 AM, Vincent Diepeveen <di...@xs...> wrote:

> hi all,
>
> Maybe one of you knows as memory migration is hot of course for
> Single Image clusters; though it's off topic for SSIC,
> maybe i should subscribe again for linux-smp list.
>
> Apologies in advance for posting it here.
>
> Default linux kernel supports memory migration since 2.6.16 kernel,
> but i wonder whether it supports it automatically as independant feature.
>
> I wonder whether at my 4 socket AMD 8356 2.3Ghz (barcelona core),
> by default linux can have a memory migration.
>
> So we had allocated 'shared' memory and written memory at socket 3 by core
> 15, now socket 0 core 1 writes at that same memory, does it get migrated
> now to socket 0 dimms?
>
> Does the realtime linux kernel have memory migration of such type by
> default, if so when does it get triggered and when not?
>
> So i'm speaking about general memory migration, not migration of memory
> when also the proces/thread migrates to another core.
>
> If it does have it by default, does it also migrate when using
> shared memory (shmget + shmat), which is what i use in my chessprogram.
>
> Thanks in advance for answerring,
> Vincent
>
>
>
>
> ------------------------------------------------------------------------------
> Nokia and AT&T present the 2010 Calling All Innovators-North America
> contest
> Create new apps & games for the Nokia N8 for consumers in  U.S. and Canada
> $10 million total in prizes - $4M cash, 500 devices, nearly $6M in
> marketing
> Develop with Nokia Qt SDK, Web Runtime, or Java and Publish to Ovi Store
> http://p.sf.net/sfu/nokia-dev2dev
> _______________________________________________
> Ssic-linux-users mailing list
> Ssi...@li...
> https://lists.sourceforge.net/lists/listinfo/ssic-linux-users
>

[SSI-users] Memory Migration in Realtime Linux Kernels

[Vincent D. <di...@xs...>]

hi all,

Maybe one of you knows as memory migration is hot of course for
Single Image clusters; though it's off topic for SSIC,
maybe i should subscribe again for linux-smp list.

Apologies in advance for posting it here.

Default linux kernel supports memory migration since 2.6.16 kernel,
but i wonder whether it supports it automatically as independant feature.

I wonder whether at my 4 socket AMD 8356 2.3Ghz (barcelona core),
by default linux can have a memory migration.

So we had allocated 'shared' memory and written memory at socket 3 by core
15, now socket 0 core 1 writes at that same memory, does it get migrated
now to socket 0 dimms?

Does the realtime linux kernel have memory migration of such type by
default, if so when does it get triggered and when not?

So i'm speaking about general memory migration, not migration of memory
when also the proces/thread migrates to another core.

If it does have it by default, does it also migrate when using
shared memory (shmget + shmat), which is what i use in my chessprogram.

Thanks in advance for answerring,
Vincent

Re: [SSI-users] setup with Fedora 3 failed with init not found

[Roger T. <rog...@gm...>]

On Tue, Oct 12, 2010 at 9:37 PM, Alceu Rodrigues de Freitas Junior <
gla...@ya...> wrote:

> Greetings
>
> I've being trying to install Fedora 3 with Openssi 1.9.2 in a machine
> with processor Intel I3 and motherboard ASUS P7H55. Since both HD and
>
> <snip>

> package), I tried to boot it and try to compile the driver, but all my
> tries finished with a
>
> Kernel panic - not syncing: no init found. Try passing init= option to
> kernel.
> Entering kbd (current=0xc19715b0, pid 2) on processor 0 due to
> KDB_ENTER()
> [0] kbd >
>
>
Looks like you need to run the OpenSSI modified /sbin/mkinitrd.  Try the
mkinitrd RPM from the OpenSSI for FC3 releases.

About the network card driver if the CentOS 4 kernel supports that card
you're in luck - once we release the OpenSSI modified CentOS 4 kernel.  No
time line on that, might be released around the same time as 2.0.0rc1 FC3
that comes with kernel-2.6.11.

-Roger

Re: [SSI-users] setup with Fedora 3 failed with init not found

[Scott W. <sc...@sl...>]

Heya,

Unless the driver explicitly supports 2.6.11 or so, you're going to
have to do a significant amount of technical work to get it to
compile.  You'll have to change code from using newer OS APIs to older
versions, or work around places where no counterpart exists.  This is
called "backporting".  It would be a lot easier to stick an old 3com
card in the machine.  Is this the same machine where you can't even
see the PCI bus?  If so, virtualization is looking better and better.

OpenSSI is pretty specific about how it boots.  Do you still have the
old grub.conf around?  Put it back and re-run ssi-ksync.  It *might*
fix things up again.  The list of things that could be mucked up is
long and technical.  Keeping good backups is probably the general
solution here.  You can try passing
init=/boot/whatever-the-openssi-init-file-for-your-kernel-is and
seeing if it comes up.  If so, it should be a matter of fixing up the
bootloader config and re-running grub.

Good luck,
-scott


On 10/12/10, Alceu Rodrigues de Freitas Junior <gla...@ya...> wrote:
> Greetings
>
> I've being trying to install Fedora 3 with Openssi 1.9.2 in a machine
> with processor Intel I3 and motherboard ASUS P7H55. Since both HD and
> DVD are SATA, I had to turn on IDE emulation on BIOS to be able to
> install Fedora 3.
>
> I have issues with the network card from this box with Fedora 3, since
> the kernel doesn't have the proper driver for it (Realtek 8168). I
> wasn't able to install OpenSSI since the setup script does expect a
> ethernet card and doesn't allow me to go further.
>
> Then I installed the kernel source from Fedora following the instruction
> here: http://www.mjmwired.net/resources/mjm-fedora-fc3.html#kernelsrc to
> try to compile the driver downloaded from Realtek website.
>
> I wasn't able to compile the driver: the insmod finished with the error:
> r8168: Unknown symbol DMA_BIT_MASK. I believe this errors occurs because
> the driver was written for newer kernel versions and such function had
> it's name changed from the a previous name.
>
> Then I tried to install the Openssi kernel provided here:
> http://prdownloads.sourceforge.net/ssic-linux/kernel-ssi-2.6.10-ssi_3devel.src.rpm?download
>
> After compiling the kernel (using the config provided by the RPM
> package), I tried to boot it and try to compile the driver, but all my
> tries finished with a
>
> Kernel panic - not syncing: no init found. Try passing init= option to
> kernel.
> Entering kbd (current=0xc19715b0, pid 2) on processor 0 due to
> KDB_ENTER()
> [0] kbd >
>
> I found some messages in the mailing list archive related to this error,
> and one of them commented about a patch that would need to be applied.
> Is this the same situation? The message is quite old (2005).
>
> Looks like I have the chicken and egg problem: I cannot install OpenSSI
> because I don't have a network card and I can't install the network
> because I don't know if the Openssi kernel will be able to allow me to
> compile the driver.
>
> Could please provide any help on that?
>
> I was able to boot with newer distributions (Ubuntu 10.04 and Fedora 11)
> and both recognize the network card. Here is more information about the
> hardware:
>
> cpuinfo:
>
> processor	: 0
> vendor_id	: GenuineIntel
> cpu family	: 6
> model		: 5
> model name	: Intel(R) Core(TM) i3 CPU         550  @ 3.20GHz
> stepping	: 5
> cpu MHz		: 3211.586
> cache size	: 32 KB
> physical id	: 0
> siblings	: 16
> fdiv_bug	: no
> hlt_bug		: no
> f00f_bug	: no
> coma_bug	: no
> fpu		: yes
> fpu_exception	: yes
> cpuid level	: 11
> wp		: yes
> flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov
> pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx lm pni
> monitor ds_cpl est tm2 xtpr
> bogomips	: 2390.01
>
> lspic:
>
> 00:00.0 Host bridge: Intel Corp.: Unknown device 0040 (rev 18)
> 00:01.0 PCI bridge: Intel Corp.: Unknown device 0041 (rev 18)
> 00:1a.0 USB Controller: Intel Corp.: Unknown device 3b3c (rev 06)
> 00:1b.0 Class 0403: Intel Corp.: Unknown device 3b56 (rev 06)
> 00:1c.0 PCI bridge: Intel Corp.: Unknown device 3b42 (rev 06)
> 00:1c.4 PCI bridge: Intel Corp.: Unknown device 3b4a (rev 06)
> 00:1c.5 PCI bridge: Intel Corp.: Unknown device 3b4c (rev 06)
> 00:1d.0 USB Controller: Intel Corp.: Unknown device 3b34 (rev 06)
> 00:1e.0 PCI bridge: Intel Corp. 82801 PCI Bridge (rev a6)
> 00:1f.0 ISA bridge: Intel Corp.: Unknown device 3b06 (rev 06)
> 00:1f.2 IDE interface: Intel Corp.: Unknown device 3b20 (rev 06)
> 00:1f.3 SMBus: Intel Corp.: Unknown device 3b30 (rev 06)
> 00:1f.5 IDE interface: Intel Corp.: Unknown device 3b26 (rev 06)
> 01:00.0 VGA compatible controller: nVidia Corporation: Unknown device
> 0a20 (rev a2)
> 01:00.1 Class 0403: nVidia Corporation: Unknown device 0be2 (rev a1)
> 02:00.0 Ethernet controller: Realtek Semiconductor Co., Ltd.: Unknown
> device 8168 (rev 03)
> 03:00.0 IDE interface: VIA Technologies, Inc.: Unknown device 0415
>
> If necessary, I can provide dmesg output.
>
> Thanks,
> Alceu
>
>
> ------------------------------------------------------------------------------
> Beautiful is writing same markup. Internet Explorer 9 supports
> standards for HTML5, CSS3, SVG 1.1,  ECMAScript5, and DOM L2 & L3.
> Spend less time writing and  rewriting code and more time creating great
> experiences on the web. Be a part of the beta today.
> http://p.sf.net/sfu/beautyoftheweb
> _______________________________________________
> Ssic-linux-users mailing list
> Ssi...@li...
> https://lists.sourceforge.net/lists/listinfo/ssic-linux-users
>

[SSI-users] setup with Fedora 3 failed with init not found

[Alceu R. de F. J. <gla...@ya...>]

Greetings

I've being trying to install Fedora 3 with Openssi 1.9.2 in a machine 
with processor Intel I3 and motherboard ASUS P7H55. Since both HD and 
DVD are SATA, I had to turn on IDE emulation on BIOS to be able to 
install Fedora 3.

I have issues with the network card from this box with Fedora 3, since 
the kernel doesn't have the proper driver for it (Realtek 8168). I 
wasn't able to install OpenSSI since the setup script does expect a 
ethernet card and doesn't allow me to go further.

Then I installed the kernel source from Fedora following the instruction 
here: http://www.mjmwired.net/resources/mjm-fedora-fc3.html#kernelsrc to 
try to compile the driver downloaded from Realtek website.

I wasn't able to compile the driver: the insmod finished with the error:
r8168: Unknown symbol DMA_BIT_MASK. I believe this errors occurs because 
the driver was written for newer kernel versions and such function had 
it's name changed from the a previous name.

Then I tried to install the Openssi kernel provided here: 
http://prdownloads.sourceforge.net/ssic-linux/kernel-ssi-2.6.10-ssi_3devel.src.rpm?download

After compiling the kernel (using the config provided by the RPM 
package), I tried to boot it and try to compile the driver, but all my 
tries finished with a

Kernel panic - not syncing: no init found. Try passing init= option to 
kernel.
Entering kbd (current=0xc19715b0, pid 2) on processor 0 due to
KDB_ENTER()
[0] kbd >

I found some messages in the mailing list archive related to this error, 
and one of them commented about a patch that would need to be applied. 
Is this the same situation? The message is quite old (2005).

Looks like I have the chicken and egg problem: I cannot install OpenSSI 
because I don't have a network card and I can't install the network 
because I don't know if the Openssi kernel will be able to allow me to 
compile the driver.

Could please provide any help on that?

I was able to boot with newer distributions (Ubuntu 10.04 and Fedora 11) 
and both recognize the network card. Here is more information about the 
hardware:

cpuinfo:

processor	: 0
vendor_id	: GenuineIntel
cpu family	: 6
model		: 5
model name	: Intel(R) Core(TM) i3 CPU         550  @ 3.20GHz
stepping	: 5
cpu MHz		: 3211.586
cache size	: 32 KB
physical id	: 0
siblings	: 16
fdiv_bug	: no
hlt_bug		: no
f00f_bug	: no
coma_bug	: no
fpu		: yes
fpu_exception	: yes
cpuid level	: 11
wp		: yes
flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov 
pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx lm pni 
monitor ds_cpl est tm2 xtpr
bogomips	: 2390.01

lspic:

00:00.0 Host bridge: Intel Corp.: Unknown device 0040 (rev 18)
00:01.0 PCI bridge: Intel Corp.: Unknown device 0041 (rev 18)
00:1a.0 USB Controller: Intel Corp.: Unknown device 3b3c (rev 06)
00:1b.0 Class 0403: Intel Corp.: Unknown device 3b56 (rev 06)
00:1c.0 PCI bridge: Intel Corp.: Unknown device 3b42 (rev 06)
00:1c.4 PCI bridge: Intel Corp.: Unknown device 3b4a (rev 06)
00:1c.5 PCI bridge: Intel Corp.: Unknown device 3b4c (rev 06)
00:1d.0 USB Controller: Intel Corp.: Unknown device 3b34 (rev 06)
00:1e.0 PCI bridge: Intel Corp. 82801 PCI Bridge (rev a6)
00:1f.0 ISA bridge: Intel Corp.: Unknown device 3b06 (rev 06)
00:1f.2 IDE interface: Intel Corp.: Unknown device 3b20 (rev 06)
00:1f.3 SMBus: Intel Corp.: Unknown device 3b30 (rev 06)
00:1f.5 IDE interface: Intel Corp.: Unknown device 3b26 (rev 06)
01:00.0 VGA compatible controller: nVidia Corporation: Unknown device 
0a20 (rev a2)
01:00.1 Class 0403: nVidia Corporation: Unknown device 0be2 (rev a1)
02:00.0 Ethernet controller: Realtek Semiconductor Co., Ltd.: Unknown 
device 8168 (rev 03)
03:00.0 IDE interface: VIA Technologies, Inc.: Unknown device 0415

If necessary, I can provide dmesg output.

Thanks,
Alceu

Re: [SSI-users] setup of OpenSSI 1.9.6 with Debian Sarge with a very old hardware

[Alceu R. de F. J. <gla...@ya...>]

Hello there Scott,

I gave a try to Fedora and had better results.

I was able to boot the node 1 server after installing OpenSSI in the AMD 
machine with Fedora 3: I just had to add the "noapic" kernel option to 
grub.conf.

After following the tutorial of Fedora3, I started making some 
configurations to try to use the old box (genuine intel processor).

I added manually some configurations into /etc/dhcpd.conf (like making 
it authoritative). Tested with another machine and it worked.

After that, the old box could not boot from the network by using only 
the boot option from BIOS. I downloaded the ISO image from Etherboot 
website and then the machine was able to boot and search for the DHCP in 
the node 1 machine.

Then I run the openssi-config-node program. Answered the questions with 
most default options (192.168.0.3 as static IP address, use Etherboot 
and node number equal 2).

After that the configuration of /etc/dhcpd.conf was modified by the 
program and all my configurations gone for good.

Then I boot the old box. It started showing booting the kernel, but 
right after that the machine rebooted again, just like when I tried to 
make this box as node 1 using Debian Sarge.

I checked the documentation "Configuring Serial Console with OpenSSI", 
and did the configuration. But after changing the script, I could not 
get anything on my serial console but garbage after trying to boot 
several times the machine.

Looking further, I found the directory pxelinux.cfg (is the tutorial 
outdated?). I edited the default file like this:

[root@master ~]# cd /tftpboot/
[root@master tftpboot]# ls
combined  initrd  kernel  pxelinux.0  pxelinux.cfg
[root@master tftpboot]# cd pxelinux.cfg/
[root@master pxelinux.cfg]# ls
default  default.bkp
[root@master pxelinux.cfg]# cat default
timeout 50
prompt 1
display disfile
default openssi
serial 0 9600

label openssi
kernel kernel
# Standard append line
#append initrd=initrd ro
# Useful for test machines with serial consoles
append initrd=initrd ro console=tty0 console=ttyS0,9600

label local
localboot 0
[root@master pxelinux.cfg]#

And finally I got something in my serial console:

<console>
Bem vindo ao minicom 2.3

OPÇÕES: I18n
Compilado em Sep 25 2009, 23:40:20.
Port /dev/ttyS0

                Pressione CTRL-A Z para ajuda sobre teclas especiais


PXELINUX 2.11 2004-08-16  Copyright (C) 1994-2004 H. Peter Anvin
boot:
Loading kernel........................................
Loading initrd..................................
Ready.
</console>

Nothing else but that.

I'll try to install Fedore 3 in this old box, install OpenSSI and see if 
it can boot after all with the OpenSSI kernel. If not, I'll try to 
compile the kernel with the processor architecture that it uses (Genuine 
Intel) and see what is happens.

Anyway, looks like a problem with the OpenSSI kernel. I shall try with 
another hardware to serve as a node 2 of the cluster and let you know.

Thanks,
Alceu

Scott Walters escreveu:
> "The machine starts booting OpenSSI"... again, what are the last few
> lines of output?
> 
> Since the screen goes black and doesn't give you a chance to read the
> messages, you should set up a serial console.  Add
> "console=ttyS0,9600" to the kernel parameters for the bootloader and
> turn off getty for ttys0 in /etc/inittab (comment the line out, if it
> isn't already).  Plug another computer in to the first serial port
> with a null modem cable or adapter, fire up a terminal program, and
> set it to keep a log.
> 
> Perhaps you want to do that on the 686 class machine, not the 586 class machine.
> 
> Looking at /usr/src/linux-source-2.6.14-ssi/.config, CONFIG_M686=y is
> uncommented, but CONFIG_M586MMX and on down are commented out/not set.
>  Perhaps I modified my copy of this file and didn't remember that fact
> though.
> 
> Cheers,
> -scott

Re: [SSI-users] initial setup for newbies

[Scott W. <sc...@sl...>]

Hi Alceu,

Reading through all of that, the situation seems to be this:

APIC isn't supported and doesn't work.

Without APIC, it can't set up interrupts for the PCI controller.

Without the PCI controller, it can't find the harddrive controller or
harddrives.

The Fedora version of OpenSSI will attempt to install and boot exactly
the same kernel.  The kernel will fail in exactly the same way if run
on the same hardware.

Short of back-porting fixes from a newer version of Linux (if you can
figure out the closest working version) to the OpenSSI kernel, I don't
have any suggestions here.

I've had good luck with ASUS motherboards with AMD CPUs but I think
you previously said that you already had a bank of machines you wanted
to cluster.

Wish I had better news for ya.

Regards,
-scott

Re: [SSI-users] initial setup for newbies

[Alceu R. de F. J. <gla...@ya...>]

Hello again Scott,

Scott Walters escreveu:

> I discovered that it's harder than I would have guessed to figure out
> if Linux supports any given PCI device by ID.  NetBSD hardcodes those
> in .h files.  I couldn't establish that supported devices on my own
> system were supported from looking at the code.  *sigh*  So trying the
> older machine (or else virtual hardware) is your best bet.

Ok, I just made some testing to grab the kernel boot messages. This will 
be a very long post, so I'm already asking the other subscribed users to 
  forgive me.

Boot 2.6.11-ssi-686-smp with the regular options:

<firstTry>
Linux version 2.6.11-ssi-686-smp (john@carbon) (gcc version 3.3.5 
(Debian 1:3.3.5-13)) #1 SMP Fri Jan 1 22:51:25 UTC 2010
BIOS-provided physical RAM map:
  BIOS-e820: 0000000000000000 - 000000000009f800 (usable)
  BIOS-e820: 000000000009f800 - 00000000000a0000 (reserved)
  BIOS-e820: 00000000000f0000 - 0000000000100000 (reserved)
  BIOS-e820: 0000000000100000 - 0000000037ee0000 (usable)
  BIOS-e820: 0000000037ee0000 - 0000000037ee3000 (ACPI NVS)
  BIOS-e820: 0000000037ee3000 - 0000000037ef0000 (ACPI data)
  BIOS-e820: 0000000037ef0000 - 0000000037f00000 (reserved)
  BIOS-e820: 0000000038000000 - 0000000040000000 (reserved)
  BIOS-e820: 00000000f0000000 - 00000000f4000000 (reserved)
  BIOS-e820: 00000000fec00000 - 0000000100000000 (reserved)
0MB HIGHMEM available.
894MB LOWMEM available.
found SMP MP-table at 000f3ac0
DMI 2.4 present.
Using APIC driver default
ACPI: PM-Timer IO Port: 0x1008
ACPI: LAPIC (acpi_id[0x00] lapic_id[0x00] enabled)
Processor #0 15:15 APIC version 16
ACPI: LAPIC (acpi_id[0x01] lapic_id[0x01] disabled)
ACPI: LAPIC (acpi_id[0x02] lapic_id[0x02] disabled)
ACPI: LAPIC (acpi_id[0x03] lapic_id[0x03] disabled)
ACPI: LAPIC_NMI (acpi_id[0x00] high edge lint[0x1])
ACPI: LAPIC_NMI (acpi_id[0x01] high edge lint[0x1])
ACPI: LAPIC_NMI (acpi_id[0x02] high edge lint[0x1])
ACPI: LAPIC_NMI (acpi_id[0x03] high edge lint[0x1])
ACPI: IOAPIC (id[0x04] address[0xfec00000] gsi_base[0])
IOAPIC[0]: apic_id 4, version 17, address 0xfec00000, GSI 0-23
ACPI: INT_SRC_OVR (bus 0 bus_irq 0 global_irq 2 dfl dfl)
ACPI: BIOS IRQ0 pin2 override ignored.
ACPI: INT_SRC_OVR (bus 0 bus_irq 9 global_irq 9 high level)
ACPI: INT_SRC_OVR (bus 0 bus_irq 14 global_irq 14 high edge)
ACPI: INT_SRC_OVR (bus 0 bus_irq 15 global_irq 15 high edge)
Enabling APIC mode:  Flat.  Using 1 I/O APICs
ACPI: HPET id: 0x10de8201 base: 0xfeff0000
Using ACPI (MADT) for SMP configuration information
Allocating PCI resources starting at 40000000 (gap: 40000000:b0000000)
Built 1 zonelists
Kernel command line: root=/dev/hda1 ro console=ttyS0,9660
Initializing CPU#0
PID hash table entries: 4096 (order: 12, 65536 bytes)
Console: colour VGA+ 80x25
Dentry cache hash table entries: 131072 (order: 7, 524288 bytes)
Inode-cache hash table entries: 65536 (order: 6, 262144 bytes)
Memory: 897148k/916352k available (3677k kernel code, 18664k reserved, 
2235k data, 272k init, 0k highmem)
Checking if this processor honours the WP bit even in supervisor mode... Ok.
hpet0: at MMIO 0xfeff0000, IRQs 2, 8, 31
hpet0: 0ns tick, 3 32-bit timers
Using HPET for base-timer
Using HPET for gettimeofday
Detected 2009.646 MHz processor.
Using hpet for high-res timesource
kdb version 4.4 by Keith Owens, Scott Lurndal. Copyright SGI, All Rights 
Reserved
kdb_cmd[0]: bpa panic_hook
Instruction(i) BP #0 at 0xc0127600 (panic_hook)
     is enabled globally adjust 1
kdb_cmd[1]: defcmd archkdb "" "First line arch debugging"
kdb_cmd[7]: defcmd archkdbcpu "" "archkdb with only tasks on cpus"
kdb_cmd[13]: defcmd archkdbshort "" "archkdb with less detailed backtrace"
kdb_cmd[19]: defcmd archkdbcommon "" "Common arch debugging"
Mount-cache hash table entries: 512 (order: 0, 4096 bytes)
VProc hash table entries: 32768 (order: 6, 262144 bytes)
CPU: L1 I Cache: 64K (64 bytes/line), D cache 64K (64 bytes/line)
CPU: L2 Cache: 256K (64 bytes/line)
Intel machine check architecture supported.
Intel machine check reporting enabled on CPU#0.
Enabling fast FPU save and restore... done.
Enabling unmasked SIMD FPU exception support... done.
Checking 'hlt' instruction... OK.
CPU0: AMD Sempron(tm) Processor LE-1150 stepping 01
Total of 1 processors activated (3973.12 BogoMIPS).
ENABLING IO-APIC IRQs
..TIMER: vector=0x31 pin1=0 pin2=-1
..MP-BIOS bug: 8254 timer not connected to IO-APIC
...trying to set up timer (IRQ0) through the 8259A ...  failed.
...trying to set up timer as Virtual Wire IRQ... failed.
...trying to set up timer as ExtINT IRQ... failed :(.
Kernel panic - not syncing: IO-APIC + timer doesn't work!  Boot with 
apic=debug and send a report.  Then try booting with the 'noapic' option
Instruction(i) breakpoint #0 at 0xc0127600 (adjusted)
0xc0127600 panic_hook:         int3

Entering kdb (current=0xc1aa3aa0, pid 2) on processor 0 due to 
Breakpoint @ 0xc0127600
[0]kdb>
</firstTry>

Booting the same kernel, with apic=debug

<secondTry>
Linux version 2.6.11-ssi-686-smp (john@carbon) (gcc version 3.3.5 
(Debian 1:3.3.5-13)) #1 SMP Fri Jan 1 22:51:25 UTC 2010
BIOS-provided physical RAM map:
  BIOS-e820: 0000000000000000 - 000000000009f800 (usable)
  BIOS-e820: 000000000009f800 - 00000000000a0000 (reserved)
  BIOS-e820: 00000000000f0000 - 0000000000100000 (reserved)
  BIOS-e820: 0000000000100000 - 0000000037ee0000 (usable)
  BIOS-e820: 0000000037ee0000 - 0000000037ee3000 (ACPI NVS)
  BIOS-e820: 0000000037ee3000 - 0000000037ef0000 (ACPI data)
  BIOS-e820: 0000000037ef0000 - 0000000037f00000 (reserved)
  BIOS-e820: 0000000038000000 - 0000000040000000 (reserved)
  BIOS-e820: 00000000f0000000 - 00000000f4000000 (reserved)
  BIOS-e820: 00000000fec00000 - 0000000100000000 (reserved)
0MB HIGHMEM available.
894MB LOWMEM available.
found SMP MP-table at 000f3ac0
DMI 2.4 present.
Unknown genapic `apic=debug' specified.
Using APIC driver default
ACPI: PM-Timer IO Port: 0x1008
ACPI: LAPIC (acpi_id[0x00] lapic_id[0x00] enabled)
Processor #0 15:15 APIC version 16
ACPI: LAPIC (acpi_id[0x01] lapic_id[0x01] disabled)
ACPI: LAPIC (acpi_id[0x02] lapic_id[0x02] disabled)
ACPI: LAPIC (acpi_id[0x03] lapic_id[0x03] disabled)
ACPI: LAPIC_NMI (acpi_id[0x00] high edge lint[0x1])
ACPI: LAPIC_NMI (acpi_id[0x01] high edge lint[0x1])
ACPI: LAPIC_NMI (acpi_id[0x02] high edge lint[0x1])
ACPI: LAPIC_NMI (acpi_id[0x03] high edge lint[0x1])
ACPI: IOAPIC (id[0x04] address[0xfec00000] gsi_base[0])
IOAPIC[0]: apic_id 4, version 17, address 0xfec00000, GSI 0-23
ACPI: INT_SRC_OVR (bus 0 bus_irq 0 global_irq 2 dfl dfl)
ACPI: BIOS IRQ0 pin2 override ignored.
ACPI: INT_SRC_OVR (bus 0 bus_irq 9 global_irq 9 high level)
ACPI: INT_SRC_OVR (bus 0 bus_irq 14 global_irq 14 high edge)
ACPI: INT_SRC_OVR (bus 0 bus_irq 15 global_irq 15 high edge)
Enabling APIC mode:  Flat.  Using 1 I/O APICs
ACPI: HPET id: 0x10de8201 base: 0xfeff0000
Using ACPI (MADT) for SMP configuration information
Allocating PCI resources starting at 40000000 (gap: 40000000:b0000000)
Built 1 zonelists
Kernel command line: root=/dev/hda1 ro apic=debug console=ttyS0,9600
Initializing CPU#0
PID hash table entries: 4096 (order: 12, 65536 bytes)
Console: colour VGA+ 80x25
Dentry cache hash table entries: 131072 (order: 7, 524288 bytes)
Inode-cache hash table entries: 65536 (order: 6, 262144 bytes)
Memory: 897148k/916352k available (3677k kernel code, 18664k reserved, 
2235k data, 272k init, 0k highmem)
Checking if this processor honours the WP bit even in supervisor mode... Ok.
hpet0: at MMIO 0xfeff0000, IRQs 2, 8, 31
hpet0: 0ns tick, 3 32-bit timers
Using HPET for base-timer
Using HPET for gettimeofday
Detected 2009.707 MHz processor.
Using hpet for high-res timesource
kdb version 4.4 by Keith Owens, Scott Lurndal. Copyright SGI, All Rights 
Reserved
kdb_cmd[0]: bpa panic_hook
Instruction(i) BP #0 at 0xc0127600 (panic_hook)
     is enabled globally adjust 1
kdb_cmd[1]: defcmd archkdb "" "First line arch debugging"
kdb_cmd[7]: defcmd archkdbcpu "" "archkdb with only tasks on cpus"
kdb_cmd[13]: defcmd archkdbshort "" "archkdb with less detailed backtrace"
kdb_cmd[19]: defcmd archkdbcommon "" "Common arch debugging"
Mount-cache hash table entries: 512 (order: 0, 4096 bytes)
VProc hash table entries: 32768 (order: 6, 262144 bytes)
CPU: L1 I Cache: 64K (64 bytes/line), D cache 64K (64 bytes/line)
CPU: L2 Cache: 256K (64 bytes/line)
Intel machine check architecture supported.
Intel machine check reporting enabled on CPU#0.
Enabling fast FPU save and restore... done.
Enabling unmasked SIMD FPU exception support... done.
Checking 'hlt' instruction... OK.
CPU0: AMD Sempron(tm) Processor LE-1150 stepping 01
Getting VERSION: 80050010
Getting VERSION: 80050010
Getting ID: 0
Getting LVT0: 700
Getting LVT1: 400
enabled ExtINT on CPU#0
ESR value before enabling vector: 0x00000004  after: 0x00000000
Total of 1 processors activated (3973.12 BogoMIPS).
ENABLING IO-APIC IRQs
Synchronizing Arb IDs.
..TIMER: vector=0x31 pin1=0 pin2=-1
..MP-BIOS bug: 8254 timer not connected to IO-APIC
...trying to set up timer (IRQ0) through the 8259A ...  failed.
...trying to set up timer as Virtual Wire IRQ... failed.
...trying to set up timer as ExtINT IRQ... failed :(.
Kernel panic - not syncing: IO-APIC + timer doesn't work!  Boot with 
apic=debug and send a report.  Then try booting with the 'noapic' option
Instruction(i) breakpoint #0 at 0xc0127600 (adjusted)
0xc0127600 panic_hook:         int3

Entering kdb (current=0xc1aa3aa0, pid 2) on processor 0 due to 
Breakpoint @ 0xc0127600
[0]kdb>
</secondTry>

Booting the same kernel, with "noapic" option:

<thirdTry>
Linux version 2.6.11-ssi-686-smp (john@carbon) (gcc version 3.3.5 
(Debian 1:3.3.5-13)) #1 SMP Fri Jan 1 22:51:25 UTC 2010
BIOS-provided physical RAM map:
  BIOS-e820: 0000000000000000 - 000000000009f800 (usable)
  BIOS-e820: 000000000009f800 - 00000000000a0000 (reserved)
  BIOS-e820: 00000000000f0000 - 0000000000100000 (reserved)
  BIOS-e820: 0000000000100000 - 0000000037ee0000 (usable)
  BIOS-e820: 0000000037ee0000 - 0000000037ee3000 (ACPI NVS)
  BIOS-e820: 0000000037ee3000 - 0000000037ef0000 (ACPI data)
  BIOS-e820: 0000000037ef0000 - 0000000037f00000 (reserved)
  BIOS-e820: 0000000038000000 - 0000000040000000 (reserved)
  BIOS-e820: 00000000f0000000 - 00000000f4000000 (reserved)
  BIOS-e820: 00000000fec00000 - 0000000100000000 (reserved)
0MB HIGHMEM available.
894MB LOWMEM available.
found SMP MP-table at 000f3ac0
DMI 2.4 present.
Using APIC driver default
ACPI: PM-Timer IO Port: 0x1008
ACPI: LAPIC (acpi_id[0x00] lapic_id[0x00] enabled)
Processor #0 15:15 APIC version 16
ACPI: LAPIC (acpi_id[0x01] lapic_id[0x01] disabled)
ACPI: LAPIC (acpi_id[0x02] lapic_id[0x02] disabled)
ACPI: LAPIC (acpi_id[0x03] lapic_id[0x03] disabled)
ACPI: LAPIC_NMI (acpi_id[0x00] high edge lint[0x1])
ACPI: LAPIC_NMI (acpi_id[0x01] high edge lint[0x1])
ACPI: LAPIC_NMI (acpi_id[0x02] high edge lint[0x1])
ACPI: LAPIC_NMI (acpi_id[0x03] high edge lint[0x1])
ACPI: Skipping IOAPIC probe due to 'noapic' option.
ACPI: HPET id: 0x10de8201 base: 0xfeff0000
Using ACPI for processor (LAPIC) configuration information
Intel MultiProcessor Specification v1.4
     Virtual Wire compatibility mode.
OEM ID: OEM00000 Product ID: PROD00000000 APIC at: 0xFEE00000
I/O APIC #4 Version 17 at 0xFEC00000.
Enabling APIC mode:  Flat.  Using 1 I/O APICs
Processors: 1
Allocating PCI resources starting at 40000000 (gap: 40000000:b0000000)
Built 1 zonelists
Kernel command line: root=/dev/hda1 ro noapic console=ttyS0,9600
Initializing CPU#0
PID hash table entries: 4096 (order: 12, 65536 bytes)
Console: colour VGA+ 80x25
Dentry cache hash table entries: 131072 (order: 7, 524288 bytes)
Inode-cache hash table entries: 65536 (order: 6, 262144 bytes)
Memory: 897148k/916352k available (3677k kernel code, 18664k reserved, 
2235k data, 272k init, 0k highmem)
Checking if this processor honours the WP bit even in supervisor mode... Ok.
hpet0: at MMIO 0xfeff0000, IRQs 2, 8, 31
hpet0: 0ns tick, 3 32-bit timers
Using HPET for base-timer
Using HPET for gettimeofday
Detected 2009.646 MHz processor.
Using hpet for high-res timesource
kdb version 4.4 by Keith Owens, Scott Lurndal. Copyright SGI, All Rights 
Reserved
kdb_cmd[0]: bpa panic_hook
Instruction(i) BP #0 at 0xc0127600 (panic_hook)
     is enabled globally adjust 1
kdb_cmd[1]: defcmd archkdb "" "First line arch debugging"
kdb_cmd[7]: defcmd archkdbcpu "" "archkdb with only tasks on cpus"
kdb_cmd[13]: defcmd archkdbshort "" "archkdb with less detailed backtrace"
kdb_cmd[19]: defcmd archkdbcommon "" "Common arch debugging"
Mount-cache hash table entries: 512 (order: 0, 4096 bytes)
VProc hash table entries: 32768 (order: 6, 262144 bytes)
CPU: L1 I Cache: 64K (64 bytes/line), D cache 64K (64 bytes/line)
CPU: L2 Cache: 256K (64 bytes/line)
Intel machine check architecture supported.
Intel machine check reporting enabled on CPU#0.
Enabling fast FPU save and restore... done.
Enabling unmasked SIMD FPU exception support... done.
Checking 'hlt' instruction... OK.
ACPI: setting ELCR to 0200 (from 8c20)
CPU0: AMD Sempron(tm) Processor LE-1150 stepping 01
Total of 1 processors activated (3973.12 BogoMIPS).
Brought up 1 CPUs
checking if image is initramfs...it isn't (bad gzip magic numbers); 
looks like an initrd
Freeing initrd memory: 1204k freed
NET: Registered protocol family 16
PCI: PCI BIOS revision 3.00 entry at 0xfa7a0, last bus=4
PCI: Using configuration type 1
mtrr: v2.0 (20020519)
ACPI: Subsystem revision 20050211
     ACPI-0352: *** Error: Looking up [\_PR_.CPU0] in namespace, 
AE_NOT_FOUND
search_node f7ed9f00 start_node f7ed9f00 return_node 00000000
ACPI: Interpreter enabled
ACPI: Using PIC for interrupt routing
ACPI: PCI Root Bridge [PCI0] (00:00)
PCI: Probing PCI hardware (bus 00)
PCI: Transparent bridge - 0000:00:04.0
ACPI: PCI Interrupt Link [LNK1] (IRQs 5 7 9 10 11 14 15) *0, disabled.
ACPI: PCI Interrupt Link [LNK2] (IRQs *5 7 9 10 11 14 15)
ACPI: PCI Interrupt Link [LNK3] (IRQs 5 7 9 10 11 14 15) *0, disabled.
ACPI: PCI Interrupt Link [LNK4] (IRQs 5 7 9 10 11 14 15) *0, disabled.
ACPI: PCI Interrupt Link [LNK5] (IRQs 5 7 9 10 11 14 15) *0, disabled.
ACPI: PCI Interrupt Link [LNK6] (IRQs 5 7 9 10 11 14 15) *0, disabled.
ACPI: PCI Interrupt Link [LNK7] (IRQs 5 7 9 10 11 14 15) *0, disabled.
ACPI: PCI Interrupt Link [LNK8] (IRQs 5 7 9 10 11 14 15) *0, disabled.
ACPI: PCI Interrupt Link [LIGP] (IRQs 5 7 9 10 *11 14 15)
ACPI: PCI Interrupt Link [LP2P] (IRQs 5 7 9 10 11 14 15) *0, disabled.
ACPI: PCI Interrupt Link [LUBA] (IRQs *5 7 9 10 11 14 15)
ACPI: PCI Interrupt Link [LMAC] (IRQs 5 7 9 10 11 14 *15)
ACPI: PCI Interrupt Link [LAZA] (IRQs 5 7 9 *10 11 14 15)
ACPI: PCI Interrupt Link [LPMU] (IRQs 5 7 9 10 *11 14 15)
ACPI: PCI Interrupt Link [LSMB] (IRQs 5 7 9 10 *11 14 15)
ACPI: PCI Interrupt Link [LUB2] (IRQs 5 7 9 *10 11 14 15)
ACPI: PCI Interrupt Link [LIDE] (IRQs 5 7 9 10 11 14 15) *0, disabled.
ACPI: PCI Interrupt Link [LSID] (IRQs 5 7 9 10 *11 14 15)
ACPI: PCI Interrupt Link [LFID] (IRQs 5 7 9 *10 11 14 15)
ACPI: PCI Interrupt Link [APC1] (IRQs 16) *0, disabled.
ACPI: PCI Interrupt Link [APC2] (IRQs 17) *0, disabled.
ACPI: PCI Interrupt Link [APC3] (IRQs 18) *0, disabled.
ACPI: PCI Interrupt Link [APC4] (IRQs 19) *0, disabled.
ACPI: PCI Interrupt Link [APC5] (IRQs 16) *0, disabled.
ACPI: PCI Interrupt Link [APC6] (IRQs 16) *0, disabled.
ACPI: PCI Interrupt Link [APC7] (IRQs 16) *0, disabled.
ACPI: PCI Interrupt Link [APC8] (IRQs 16) *0, disabled.
ACPI: PCI Interrupt Link [AIGP] (IRQs 20 21 22) *0, disabled.
ACPI: PCI Interrupt Link [APCF] (IRQs 20 21 22) *0, disabled.
ACPI: PCI Interrupt Link [APCH] (IRQs 20 21 22) *0, disabled.
ACPI: PCI Interrupt Link [APMU] (IRQs 20 21 22) *0, disabled.
ACPI: PCI Interrupt Link [AAZA] (IRQs 20 21 22) *0, disabled.
ACPI: PCI Interrupt Link [APCS] (IRQs 20 21 22) *0, disabled.
ACPI: PCI Interrupt Link [APCL] (IRQs 20 21 22) *0, disabled.
ACPI: PCI Interrupt Link [APCM] (IRQs 20 21 22) *0, disabled.
ACPI: PCI Interrupt Link [APCZ] (IRQs 20 21 22) *0, disabled.
ACPI: PCI Interrupt Link [APSI] (IRQs 23) *0, disabled.
ACPI: PCI Interrupt Link [APSJ] (IRQs 23) *0, disabled.
Linux Plug and Play Support v0.97 (c) Adam Belay
pnp: PnP ACPI init
pnp: PnP ACPI: found 13 devices
usbcore: registered new driver usbfs
usbcore: registered new driver hub
PCI: Using ACPI for IRQ routing
** PCI interrupts are no longer routed automatically.  If this
** causes a device to stop working, it is probably because the
** driver failed to call pci_enable_device().  As a temporary
** workaround, the "pci=routeirq" argument restores the old
** behavior.  If this argument makes the device work again,
** please email the output of "lspci" to bjo...@hp...
** so I can fix the driver.
pnp: 00:00: ioport range 0x1000-0x107f could not be reserved
pnp: 00:00: ioport range 0x1080-0x10ff has been reserved
pnp: 00:00: ioport range 0x1400-0x147f has been reserved
pnp: 00:00: ioport range 0x1480-0x14ff could not be reserved
pnp: 00:00: ioport range 0x1800-0x187f has been reserved
pnp: 00:00: ioport range 0x1880-0x18ff has been reserved
pnp: 00:00: ioport range 0x2000-0x207f has been reserved
pnp: 00:00: ioport range 0x2080-0x20ff has been reserved
apm: BIOS version 1.2 Flags 0x07 (Driver version 1.16ac)
apm: overridden by ACPI.
audit: initializing netlink socket (disabled)
audit(1285185009.071:0): initialized
Total HugeTLB memory allocated, 0
VFS: Disk quotas dquot_6.5.1
Dquot-cache hash table entries: 1024 (order 0, 4096 bytes)
Initializing Cryptographic API
CFS server token hash table entries: 131072 (order: 7, 524288 bytes)
SSI Token Message hash table entries: 4096 (order: 3, 32768 bytes)
pci_hotplug: PCI Hot Plug PCI Core version: 0.5
ACPI: Fan [FAN] (on)
     ACPI-0352: *** Error: Looking up [\_PR_.CPU0] in namespace, 
AE_NOT_FOUND
search_node f7ed9f00 start_node f7ed9f00 return_node 00000000
ACPI: Thermal Zone [THRM] (19 C)
isapnp: Scanning for PnP cards...
isapnp: No Plug & Play device found
Real Time Clock Driver v1.12
hpet_acpi_add: no address or irqs in _CRS
Linux agpgart interface v0.100 (c) Dave Jones
[drm] Initialized drm 1.0.0 20040925
ACPI: PS/2 Keyboard Controller [PS2K] at I/O 0x60, 0x64, irq 1
serio: i8042 KBD port at 0x60,0x64 irq 1
Serial: 8250/16550 driver $Revision: 1.90 $ 76 ports, IRQ sharing enabled
ÿttyS0 at I/O 0x3f8 (irq = 4) is a 16550A
ttyS0 at I/O 0x3f8 (irq = 4) is a 16550A
io scheduler noop registered
io scheduler anticipatory registered
io scheduler deadline registered
io scheduler cfq registered
RAMDISK driver initialized: 16 RAM disks of 16384K size 1024 blocksize
Uniform Multi-Platform E-IDE driver Revision: 7.00alpha2
ide: Assuming 33MHz system bus speed for PIO modes; override with idebus=xx
hda: SAMSUNG SP0411N, ATA DISK drive
hdb: HL-DT-STDVDRRW GWA-4161B, ATAPI CD/DVD-ROM drive
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
hda: max request size: 1024KiB
hda: 78242976 sectors (40060 MB) w/2048KiB Cache, CHS=16383/255/63
  hda: hda1 hda2 < hda5 hda6 hda7 hda8 hda9 >
hdb: ATAPI 40X DVD-ROM DVD-R CD-R/RW drive, 2048kB Cache
Uniform CD-ROM driver Revision: 3.20
ide-floppy driver 0.99.newide
usbcore: registered new driver hiddev
usbcore: registered new driver usbhid
drivers/usb/input/hid-core.c: v2.0:USB HID core driver
mice: PS/2 mouse device common for all mice
input: AT Translated Set 2 keyboard on isa0060/serio0
md: md driver 0.90.1 MAX_MD_DEVS=256, MD_SB_DISKS=27
NET: Registered protocol family 2
IP: routing cache hash table of 8192 buckets, 64Kbytes
TCP established hash table entries: 131072 (order: 8, 1048576 bytes)
TCP bind hash table entries: 65536 (order: 7, 524288 bytes)
TCP: Hash tables configured (established 131072 bind 65536)
IPVS: Registered protocols (TCP, UDP, AH, ESP)
IPVS: Connection hash table configured (size=65536, memory=512Kbytes)
IPVS: ipvs loaded.
IPVS: [wlc] scheduler registered.
Initializing IPsec netlink socket
NET: Registered protocol family 1
NET: Registered protocol family 10
IPv6 over IPv4 tunneling driver
NET: Registered protocol family 17
ACPI wakeup devices:
HUB0 XVR0 XVR1 XVR2 UAR1 USB0 USB2 AZAD MMAC
ACPI: (supports S0 S3 S4 S5)
md: Autodetecting RAID arrays.
md: autorun ...
md: ... autorun DONE.
RAMDISK: cramfs filesystem found at block 0
RAMDISK: Loading 1204KiB [1 disk] into ram disk... |/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\done.
Kernel panic - not syncing: VFS: Unable to mount root fs on 
unknown-block(1,0)
Instruction(i) breakpoint #0 at 0xc0127600 (adjusted)
0xc0127600 panic_hook:         int3

Entering kdb (current=0xc1aa3aa0, pid 2) on processor 0 due to 
Breakpoint @ 0xc0127600
[0]kdb>
</thirdTry>


That it. I'll give a try to Fedore 3 now.

Thanks in advance,
Alceu

Re: [SSI-users] setup of OpenSSI 1.9.6 with Debian Sarge with a very old hardware

[Alceu R. de F. J. <gla...@ya...>]

Hello Scott,

I commented your e-mail below:

Scott Walters escreveu:
> 
> Since the screen goes black and doesn't give you a chance to read the
> messages, you should set up a serial console.  Add
> "console=ttyS0,9600" to the kernel parameters for the bootloader and
> turn off getty for ttys0 in /etc/inittab (comment the line out, if it
> isn't already).  Plug another computer in to the first serial port
> with a null modem cable or adapter, fire up a terminal program, and
> set it to keep a log.

Ok, I did that. But I still didn't get anything.

The last words I got from trying to boot the SSI kernel is "boot". Just 
before that, just the lines from the configuration done in GRUB:

Booting command-list

root (hd0,0)
  Filesystem type is ext2fs, partition type 0x83
kernel /boot/vmlinuz02.6.11-ssi-686-smp root=/dev/hda1 ro console=ttyS0,9600
     [Linux-bzImage, setup=0x1600, size=0x2546ef]
initrd /boot/initrd.img-2.6.11-ssi-686-smp
     [Linux-initrd @ 0x5a55000, 0x19a36f bytes]
savedefault
boot

Then I tried the same parameters with Debian Sarge vanilla kernel, and 
it just worked. I just had to put 9600 instead of 16500 (which I did use 
when trying to connect to the machine by using the null modem cable and 
got a working prompt after that). I do have the output from it, but it's 
218 lines length and I don't if it's interesting to post it here. Please 
let me know if I should do it.

After that, I went out compiling the vanilla Debian kernel source 
(2.6.8) just changing the processor type to "Genuine Intel" and putting 
the EXT3 in the kernel instead of using a module. After that, I 
installed the kernel, executed a boot with it and got the same error 
that I got with another box that uses a AMD Sempron processor:

VFS: Cannot open root device "hda1" or unknown block(0,0)
Please append a correct "root=" boot option
Kernel panic: VFS

This was exactly the same error I got with the Sempron machine.

Finally, I did another test: installed Debian Sarge by the same way 
described BUT did not installed anything related to OpenSSI, neither 
used the OpenSSI repository for packages.

Then I just download the source for kernel 2.6.8 and did the same 
configuration, compiled the kernel and it boot with any problem.

> Perhaps you want to do that on the 686 class machine, not the 586 class machine.

I'll do it, just to provide more information about the setup process.

> Looking at /usr/src/linux-source-2.6.14-ssi/.config, CONFIG_M686=y is
> uncommented, but CONFIG_M586MMX and on down are commented out/not set.
>  Perhaps I modified my copy of this file and didn't remember that fact
> though.

I really don't know if this is bug in the OpenSSI kernel, but I would 
test any modification you could provide regarding that.

I did these errors during my last setup with OpenSSI packages:

cpio: initrd/lib/libcluster.so.0 not created: newer or same age version 
exists
cpio: initrd/lib/tls/libc.so.6 not created: newer or same age version exists
cpio: ./dev/cciss: No such file or directory
cpio: ./dev/ida: No such file or directory
cpio: ./dev/ide: No such file or directory
cpio: ./dev/mapper: No such file or directory
cpio: ./dev/scsi: No such file or directory

I did notice that there is a kernel-ssi-image-2.6.11-386 package in the 
OpenSSI repository, but that is a problem with dependency of another 
package (kernel-image) which is not available in the repository.

Do you think it would be valid to try to compile the OpenSSI kernel 
source, just changing the processor type?

Thanks in advance,
Alceu

Re: [SSI-users] contributing with OpenSSI project

[Roger T. <rog...@gm...>]

On Thu, Sep 16, 2010 at 2:42 PM, Alceu R. de Freitas Jr. <
gla...@ya...> wrote:

> Hi there Roger,
>
> >
> >De: Roger Tsang <rog...@gm...>
> >Para: Alceu Rodrigues de Freitas Junior <gla...@ya...>
> >Cc: ssi...@li...
> >Enviadas: Quinta-feira, 16 de Setembro de 2010 12:26:48
> >Assunto: Re: [SSI-users] contributing with OpenSSI project
> >
> >Create an account at http://wiki.openssi.org
> >
>
> Ok, but I had updated the original document from the Sourceforge CVS, which
> is
> in LaTEX format. :-) How should I convert it to wiki markup?
>
> Anyway, the old version of the documentation (which is a bit outdated) will
> still be visible to new users. What do you think?
>
> Regards,
> Alceu
>
>
Hi Alceu,

Ah I see.  Send your updated files and we will check-in to CVS for you.

-Roger

[SSI-users] Res: contributing with OpenSSI project

[Alceu R. de F. Jr. <gla...@ya...>]

Hi there Roger,

>
>De: Roger Tsang <rog...@gm...>
>Para: Alceu Rodrigues de Freitas Junior <gla...@ya...>
>Cc: ssi...@li...
>Enviadas: Quinta-feira, 16 de Setembro de 2010 12:26:48
>Assunto: Re: [SSI-users] contributing with OpenSSI project
>
>Create an account at http://wiki.openssi.org
>

Ok, but I had updated the original document from the Sourceforge CVS, which is 
in LaTEX format. :-) How should I convert it to wiki markup?

Anyway, the old version of the documentation (which is a bit outdated) will 
still be visible to new users. What do you think?

Regards,
Alceu



      

Re: [SSI-users] contributing with OpenSSI project

[Roger T. <rog...@gm...>]

Create an account at http://wiki.openssi.org

On Wed, Sep 15, 2010 at 8:08 PM, Alceu Rodrigues de Freitas Junior <
gla...@ya...> wrote:

> Greetings,
>
> I would like to contribute with OpenSSI project with documentation (I
> have several notes regarding version 1.9.6 on Debian Sarge) and maybe
> with kernel packages from different processor architectures.
>
> How do I do that?
>
> Thanks,
> Alceu
>
>
>
> ------------------------------------------------------------------------------
> Start uncovering the many advantages of virtual appliances
> and start using them to simplify application deployment and
> accelerate your shift to cloud computing.
> http://p.sf.net/sfu/novell-sfdev2dev
> _______________________________________________
> Ssic-linux-users mailing list
> Ssi...@li...
> https://lists.sourceforge.net/lists/listinfo/ssic-linux-users
>

[SSI-users] contributing with OpenSSI project

[Alceu R. de F. J. <gla...@ya...>]

Greetings,

I would like to contribute with OpenSSI project with documentation (I 
have several notes regarding version 1.9.6 on Debian Sarge) and maybe 
with kernel packages from different processor architectures.

How do I do that?

Thanks,
Alceu

Re: [SSI-users] setup of OpenSSI 1.9.6 with Debian Sarge with a very old hardware

[Scott W. <sc...@sl...>]

"The machine starts booting OpenSSI"... again, what are the last few
lines of output?

Since the screen goes black and doesn't give you a chance to read the
messages, you should set up a serial console.  Add
"console=ttyS0,9600" to the kernel parameters for the bootloader and
turn off getty for ttys0 in /etc/inittab (comment the line out, if it
isn't already).  Plug another computer in to the first serial port
with a null modem cable or adapter, fire up a terminal program, and
set it to keep a log.

Perhaps you want to do that on the 686 class machine, not the 586 class machine.

Looking at /usr/src/linux-source-2.6.14-ssi/.config, CONFIG_M686=y is
uncommented, but CONFIG_M586MMX and on down are commented out/not set.
 Perhaps I modified my copy of this file and didn't remember that fact
though.

Cheers,
-scott



On 9/15/10, Alceu Rodrigues de Freitas Junior <gla...@ya...> wrote:
> Scott Walters escreveu:
>> I don't understand the logic behind trying to recompile kernels.  In
>> the old days of probing ISA cards, the wrong set of actual hardware
>> and drivers built-in to the kernel could cause crashes on boot, but
>> that sort of thing is very rare these days.
>>
>> Boot the OpenSSI kernel and if the machine freezes during boot, post
>> the last several console lines.
>
> This is the original post where I commented about the issue with this
> machine: http://marc.info/?l=ssic-linux-users&m=128409498003227&w=2
>
> I decided it's was a better idea to create a new thread for it, but I
> forgot to mention that I could not get any error from the boot: the
> machine starts booting OpenSSI kernel, the screen gets black and the
> machine is rebooted. The machine get into a infinite looping because of
> that, always rebooting.
>
> My guess is because the kernel of OpenSSI is for 686 systems, so that's
> why I'm trying to compile the kernel to match it's processor. I can boot
>   with the original kernel from Debian, which was compiled for 386
> processors.
>
> Anyway, it's only a guess because I really don't think about any other
> test that could be done in such situation. I would appreciate any help
> with that.
>
> Thanks in advance,
> Alceu
>
>
>
>

Re: [SSI-users] setup of OpenSSI 1.9.6 with Debian Sarge with a very old hardware

[Alceu R. de F. J. <gla...@ya...>]

Scott Walters escreveu:
> I don't understand the logic behind trying to recompile kernels.  In
> the old days of probing ISA cards, the wrong set of actual hardware
> and drivers built-in to the kernel could cause crashes on boot, but
> that sort of thing is very rare these days.
> 
> Boot the OpenSSI kernel and if the machine freezes during boot, post
> the last several console lines.

This is the original post where I commented about the issue with this 
machine: http://marc.info/?l=ssic-linux-users&m=128409498003227&w=2

I decided it's was a better idea to create a new thread for it, but I 
forgot to mention that I could not get any error from the boot: the 
machine starts booting OpenSSI kernel, the screen gets black and the 
machine is rebooted. The machine get into a infinite looping because of 
that, always rebooting.

My guess is because the kernel of OpenSSI is for 686 systems, so that's 
why I'm trying to compile the kernel to match it's processor. I can boot 
  with the original kernel from Debian, which was compiled for 386 
processors.

Anyway, it's only a guess because I really don't think about any other 
test that could be done in such situation. I would appreciate any help 
with that.

Thanks in advance,
Alceu